Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11933
    Prev
    Next
    INDEX
    Explanations

    sequence length, consecutive occurrences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ------↵
    -0.09
     fundamentally
    -0.09
     prof
    -0.08
     investors
    -0.08
    .sort
    -0.08
    .percent
    -0.08
     Nobel
    -0.08
    fläche
    -0.08
     sorting
    -0.08
    ****↵
    -0.08
    POSITIVE LOGITS
     Tracking
    0.10
     Reset
    0.10
    	reset
    0.09
     reset
    0.09
     resets
    0.09
    Reset
    0.09
    reset
    0.09
    -reset
    0.09
     vigilance
    0.09
     resetting
    0.09
    Activations Density 0.008%

    No Known Activations